40
submitted 9 hours ago by Maroon@lemmy.world to c/opensource@lemmy.ml

I came across tools like nightshade that can poison images. That way, if someone steals an artist's work to train their AI, it learns the wrong stuff and can potentially begin spewing gibberish.

Is there something that I can use on PDFs? There are two scenarios for me:

  1. Content that I already created that is available as a pdf.
  2. I use LaTeX to make new documents and I want to poison those from scratch if possible rather than an ad hoc step once the PDF is created.
you are viewing a single comment's thread
view the rest of the comments
[-] DragonsInARoom@lemmy.world 6 points 8 hours ago

Put the word stolen at the end of every document, the llm will learn that the word stolen is normal and should be included

this post was submitted on 07 Feb 2025
40 points (87.0% liked)

Open Source

32606 readers
564 users here now

All about open source! Feel free to ask questions, and share news, and interesting stuff!

Useful Links

Rules

Related Communities

Community icon from opensource.org, but we are not affiliated with them.

founded 5 years ago
MODERATORS